© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127911
    Prev
    Next
    INDEX
    Explanations

    code block ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    っていましたが
    -1.38
     OkHttpClient
    -1.21
    ÑO
    -1.12
     IconData
    -1.11
    icated
    -1.10
    şk
    -1.09
    АО
    -1.09
     Abbiamo
    -1.08
     Siamo
    -1.07
    licante
    -1.06
    POSITIVE LOGITS
    ↵↵
    2.30
    Fakta
    1.27
    之时
    1.20
    ↵↵↵
    1.16
    之际
    1.13
     徒歩
    1.10
    Buat
    1.09
     remain
    1.06
    Ciri
    1.04
    Выводы
    1.03
    Activations Density 0.012%

    No Known Activations